Penerapan Metode YOLOv8 untuk Deteksi Jalan Berlubang Berbasis Object Detection
DOI:
https://doi.org/10.30865/jurikom.v13i1.9441Keywords:
YOLOv8, Potholes, Object Detection, Roboflow, SafetyAbstract
Road infrastructure damage, particularly potholes, is a critical issue that contributes to an increased risk of traffic accidents in Indonesia. This condition highlights the need for a road monitoring system that is capable of operating quickly, accurately, and continuously. This study aims to develop and evaluate an automated pothole detection system based on computer vision using the YOLOv8 (You Only Look Once version 8) method, a deep learning algorithm designed for real-time object detection. Dataset collection was conducted through two approaches, namely acquiring data from the Kaggle platform and capturing real-world road images directly using a smartphone camera to enhance data diversity and represent actual road conditions. All collected images were annotated using the Roboflow platform to generate labeled data suitable for model training. The YOLOv8 model was trained using a total of 345 images, consisting of 241 training images, 69 validation images, and 35 testing images. The training results indicate that the model achieved a mean Average Precision (mAP) of 93%, with a precision of 88% and a recall of 82%, demonstrating strong detection and localization performance. Furthermore, real-time testing using a smartphone camera showed that the system achieved an accuracy of over 85% under real-world conditions. These findings demonstrate that YOLOv8 has strong potential as an efficient and reliable automated pothole detection system, supporting road infrastructure maintenance and enhancing road user safety
References
[1] J.-P. Rodrigue, The Geography of Transport Systems, 6th Editio. 2024. doi: https://doi.org/10.4324/9781003343196.
[2] S. A. Rosyidah, A. Z. Z. Ismanafi, A. Putra, S. Khoirudin, W. P. Soeprapto, and U. T. Madura, “Pentingnya infrastruktur jalan bagi aksesbilitas ekonomi dan sosial terhadap warga desa sambongrejo dan desa sendangagung bojonegoro,” vol. 2, no. 10, 2024.
[3] E. M. A.T. Papagiannakis, Pavement Design and Materials. Canada, 2024. doi: https://lccn.loc.gov/2024007662.
[4] Statistik B P, “Hasil Sensus Penduduk 2020,” Badan Pus. Stat., 2020.
[5] BPS, “Badan Pusat Statistik (Statistik Transportasi Darat 2023),” 2023.
[6] A. W. Hidayat and S. R. L. Utami, “Analisis Penyebab Kecelakaan Lalu Lintas Di Kota Semarang,” J. Kaji. Tek. Sipil, vol. 5, no. 1, pp. 28–35, 2020, doi: 10.52447/jkts.v5i1.4111.
[7] Suhardi Aras, “Deteksi Jalan Berlubang Menggunakan Algoritma Yolov5,” J. Digit. Bus. Inf. Technol. Deteksi, vol. 01, no. 1, pp. 1–8, 2024, doi: 10.23971/jobit.v1i1.198.
[8] E. Setiadi et al., “Klasifikasi dan Deteksi Keretakan Pada Trotoar Menggunakan Metode Convolutional Neural Network Keywords : Road Crack Detection ; CNN ; Web Deep Learning Jalan merupakan prasarana transportasi darat yang meliputi segala bagian jalan dari badan jalan , term,” pp. 411–425, 2024.
[9] and Y. Z. Long Cheng, Dan Zhang, “Road Object Detection in Foggy Complex Scenes Based on Improved YOLOv8,” IEEE Access, vol. 12, no. August, pp. 107420–107430, 2024, doi: 10.1109/ACCESS.2024.3438612.
[10] X. Liu, Y. Chu, Y. Hu, and N. Zhao, “Enhancing Intelligent Road Target Monitoring: A Novel BGS YOLO Approach Based on the YOLOv8 Algorithm,” IEEE Open J. Intell. Transp. Syst., vol. 5, no. August, pp. 509–519, 2024, doi: 10.1109/OJITS.2024.3449698.
[11] D. D. Van, “Application of Advanced Deep Convolutional Neural Networks for the Recognition of Road Surface Anomalies,” Eng. Technol. Appl. Sci. Res., vol. 13, no. 3, pp. 10765–10768, 2023, doi: 10.48084/etasr.5890.
[12] J. Zeng and H. Zhong, “YOLOv8-PD: an improved road damage detection algorithm based on YOLOv8n model,” Sci. Rep., vol. 14, no. 1, pp. 1–14, 2024, doi: 10.1038/s41598-024-62933-z.
[13] Y. T. Penangsang and I. A. Muntaha, “Mendeteksi Jalan Berlubang Menggunakan Deep Learning,” vol. 03, no. 01, pp. 1–6, 2025.
[14] L. G. Denaro and R. Lim, “Analisis Deteksi Kerusakan pada Jalan Aspal menggunakan Deep Learning untuk Mendukung Efisiensi Biaya dan Waktu dalam Pemantauan Berkelanjutan,” J. Dimens. Ins. Prof., vol. 3, no. 1, pp. 16–25, 2025, doi: 10.9744/jdip.3.1.16-25.
[15] S. Zhang, Z. Liu, K. Wang, W. Huang, and P. Li, “OBC-YOLOv8 : an improved road damage detection model based on YOLOv8,” no. 2010, 2025, doi: 10.7717/peerj-cs.2593.
[16] P. R. Gustyanto Firgiawan, Nazwa Lintang Seina, “Implementasi Metode You Only Look Once (YOLO) untuk Pendeteksi Objek dengan Tools OpenCV,” J. Artif. Intel. dan Sist. Penunjang Keputusan, vol. 2, no. 2, pp. 137–141, 2024, [Online]. Available: https://jurnalmahasiswa.com/index.php/aidanspk
[17] A. I. Pradana, “Deteksi Rambu Lalu Lintas Real-Time di Indonesia dengan Penerapan YOLOv11 : Solusi Untuk Keamanan Berkendara,” pp. 145–155, 2024, doi: 10.33364/algoritma/v.21-2.2106.
[18] N. Khairunisa et al., “Analisis perbandingan algoritma cnn dan yolo dalam mengidentifikasi kerusakan jalan,” vol. 12, no. 3, 2024.
[19] N. Untuk, K. Penyakit, T. Padi, C. Of, and R. Plant, “Optimasi hyperparameter convolutional neural network untuk klasifikasi penyakit tanaman padi,” 2022.
[20] H. Yugaswara, H. Wicaksono, and F. T. Informasi, “Sistem komputasi paralel menggunakan gpu berbasis nvidia cuda,” vol. 17, no. 2, pp. 158–164, 2021.
